Journal ArticleDOI
Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval
Reads0
Chats0
TLDR
This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections by proposing a simple and efficient alternating minimization algorithm, dubbed iterative quantization (ITQ), and demonstrating an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.Abstract:
This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections. We formulate this problem in terms of finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube, and propose a simple and efficient alternating minimization algorithm to accomplish this task. This algorithm, dubbed iterative quantization (ITQ), has connections to multiclass spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). The resulting binary codes significantly outperform several other state-of-the-art methods. We also show that further performance improvements can result from transforming the data with a nonlinear kernel mapping prior to PCA or CCA. Finally, we demonstrate an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.read more
Citations
More filters
Journal ArticleDOI
Unsupervised Deep Pairwise Hashing
Ye Ma,Qin Li,Xia Shi,Zhenhua Guo +3 more
TL;DR: This paper creates an ensemble anchor-based pairwise similarity matrix and proposes a novel loss function to directly and robustly take advantage of the similarity and dissimilarity information via a weighted cross-entropy loss, and make use of a square loss to reduce the gap between latent binary vectors and binary codes.
Proceedings ArticleDOI
Image retrieval based on ResNet and ITQ
TL;DR: A new supervised hashing framework based on deep Residual Networks and Iterative Quantization hashing is proposed which exploits the learning abilities of deep residual network to mine the inherent hidden relationship of image content, extract deep feature descriptors, and increase the visual expression of images.
Journal ArticleDOI
Binary Representation via Jointly Personalized Sparse Hashing
TL;DR: This work proposes an effective unsupervised method, namely Jointly Personalized Sparse Hashing (JPSH), for binary representation learning, and incorporates the proposed PSH and manifold-based hash learning into the seamless formulation.
Proceedings ArticleDOI
A Saliency Guided Shallow Convolutional Neural Network for Traffic Signs Retrieval
TL;DR: A saliency guided shallow convolutional neural network for traffic signs accurate and fast retrieval is proposed by unifying deep saliency and hashing learning in a single architecture, which is scalable on large-scale datasets.
Journal ArticleDOI
DSHPoolF: deep supervised hashing based on selective pool feature map for image retrieval
P. Arulmozhi,S. Abirami +1 more
TL;DR: For enhancing the image retrieval accuracy through exploring spatial information, a novel way of deep supervised hashing based on Pooled Feature map (DSHPoolF) is proposed to generate compact hash codes that explore the spatial information by weighing the informative Feature maps from the last pooling layer.
References
More filters
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
Journal Article
LIBLINEAR: A Library for Large Linear Classification
TL;DR: LIBLINEAR is an open source library for large-scale linear classification that supports logistic regression and linear support vector machines and provides easy-to-use command-line tools and library calls for users and developers.
Journal ArticleDOI
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Aude Oliva,Antonio Torralba +1 more
TL;DR: The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.